Update app.py

app.py

@@ -8,32 +8,44 @@ def get_grayscale(image):
     return cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
 
 def thresholding(src):
-    return cv2.threshold(src,127,255, cv2.THRESH_TOZERO)[1]
+    return cv2.threshold(src, 127, 255, cv2.THRESH_TOZERO)[1]
 
 def ocr_with_easy(img):
-    gray_scale_image = get_grayscale(img)
-    thresholded_image = thresholding(gray_scale_image)
-    cv2.imwrite('image.png', thresholded_image)
     reader = easyocr.Reader(['en'])
-    bounds = reader.readtext('image.png', paragraph="False", detail=0)
+    bounds = reader.readtext(img, paragraph="False", detail=0)
     bounds = ''.join(bounds)
     return bounds
 
-def generate_ocr(img):
+def process_image(img, steps):
+    for step in steps:
+        if step == "Grayscale Conversion":
+            img = get_grayscale(img)
+        elif step == "Thresholding":
+            img = thresholding(img)
+    cv2.imwrite('processed_image.png', img)
+    return 'processed_image.png'
+
+def generate_ocr(img, steps):
     text_output = ''
-    if (img).any():
-        if img is not None:
-            text_output = ocr_with_easy(img)
-        else:
-            raise gr.Error("Please upload an image!!!!")
+    if img is not None and (img).any():
+        processed_image_path = process_image(img, steps)
+        text_output = ocr_with_easy(processed_image_path)
+    else:
+        raise gr.Error("Please upload an image and select the processing steps!")
     return text_output
 
+# Interactive tutorial steps
+tutorial_steps = [
+    "Grayscale Conversion",
+    "Thresholding"
+]
+
 # Interactive questions
 questions = [
     {
         "question": "What is the first step in OCR?",
-        "options": ["Binarization", "Grayscale conversion", "Edge detection"],
-        "answer": "Grayscale conversion"
+        "options": ["Binarization", "Grayscale Conversion", "Edge Detection"],
+        "answer": "Grayscale Conversion"
     },
     {
         "question": "What is the purpose of thresholding in OCR?",
@@ -95,16 +107,18 @@ Optical Character Recognition (OCR) is a technology used to convert different ty
 2. **Thresholding:** This step converts the grayscale image into a binary image, where the text is in black, and the background is in white. This makes it easier for the OCR algorithm to distinguish text from the background.
 3. **OCR using EasyOCR:** We use the EasyOCR library to recognize and extract text from the preprocessed image.
 
-Now that you understand the basics, you can try the OCR tool below and then proceed to answer the questions in the other tabs.
+**Interactive Tutorial:**
+Please upload an image and select the correct order of steps to perform OCR.
 """
 
 image = gr.Image()
-output = gr.Textbox(label="Output")
+steps = gr.CheckboxGroup(choices=tutorial_steps, label="Select and order the steps for OCR")
+output = gr.Textbox(label="OCR Output")
 explanation = gr.Markdown(explanation_text)
 
 ocr_app = gr.Interface(
     fn=generate_ocr,
-    inputs=image,
+    inputs=[image, steps],
     outputs=output,
     title="Optical Character Recognition",
     description=explanation_text,
@@ -119,3 +133,4 @@ quiz_app = gr.TabbedInterface(
 
 quiz_app.launch()
 
+